traject 3.3.0 → 3.7.0

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1700077d5c2d3c667fc9520b659c3ca986b8ab34aee233f62bd7f73fdef91977
-  data.tar.gz: 736b217f209ed08faba9c1d20c006b29586aa3ebdf088a89e37f5f3b7400de06
+  metadata.gz: 7ffc677e0ebb13e01b852a1d59ddfdd3cd9906142520e0c296f69ebb0eeb7429
+  data.tar.gz: 61b0e966f6ecd4d27e757e4cfc1057c72ac6deca5ad119c78ff883c246744814
 SHA512:
-  metadata.gz: 21877d6cd5b03f7ffbbac316a6d58a3bc65b534cb7457e57d39ba470ad49d99c8677e5e6ede25c650bba5ac3f0b22f9b348ebabb36ac4047433eb8a76379ef1d
-  data.tar.gz: 4ec1938d2d7b60a61ebde4e9c4e763e511c2896788b56b38ad6f22615dffb57449e29c9ef40e261952e125b90f5fe491fa447b077c7dcb1c55f57d6ef603fd5b
+  metadata.gz: 8240b450b27df011c2ff998c24c612f44bdd21a2fde5fbab996ffe509f3fc45cec7a8a8947e385a35d06f5bd8ed19732287e8f2d3dab682cc6295f7320f8dfab
+  data.tar.gz: f5dbcb44edb8d37a4e74cd1255aa1b05b638913337577c92d4fa276150c023b9e29823cc2b20ef050b33879ec63d76194d0202697d7c858a7aacd3d08241dcce

data/.github/workflows/ruby.yml

@@ -0,0 +1,35 @@
+name: CI
+
+on:
+  push:
+    branches: [ master ]
+  pull_request:
+    branches: ['**']
+
+jobs:
+  tests:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        ruby: [ '2.4', '2.5', '2.6', '2.7', '3.0', 'jruby-9.1', 'jruby-9.2' ]
+    name: Ruby ${{ matrix.ruby }}
+    steps:
+    - uses: actions/checkout@v2
+
+    - name: Set up Ruby
+      uses: ruby/setup-ruby@v1
+      with:
+        ruby-version: ${{ matrix.ruby }}
+
+    - name: set JAVA_OPTS for jruby-9.1
+      run: echo 'JAVA_OPTS="--add-opens java.base/java.security.cert=ALL-UNNAMED --add-opens java.base/java.security=ALL-UNNAMED --add-opens java.base/java.util.zip=ALL-UNNAMED"' >> $GITHUB_ENV
+      if: ${{ matrix.ruby == 'jruby-9.1' }}
+      # https://github.com/jruby/jruby/issues/4834
+      # Still seems to be an issue in jruby-9.1, but not 9.2
+      # https://github.community/t/conditional-setting-of-env-variables-in-gh-actions/179650
+
+    - name: Install dependencies
+      run: bundle install --jobs 4 --retry 3
+    - name: Run tests
+      run: bundle exec rake

data/CHANGES.md

@@ -1,12 +1,33 @@
 # Changes
 
-## Next
+## NEXT
 
 *
 
 *
 
-*
+## 3.7.0
+
+* Add two new transformation macros, `Traject::Macros::Transformation.delete_if` and `Traject::Macros::Transformations.select`.
+
+## 3.6.0
+
+* Tiny backward compat changes for ruby 3.0 compat. https://github.com/traject/traject/pull/263
+
+* Allow gem `http` 5.x in gemspec. https://github.com/traject/traject/pull/269
+
+## 3.5.0
+
+* `traject -v` and `traject -h` correctly return 0 exit code indicating success.
+
+* upgrade to slop gem  4.x, which carries with it a slightly different format of human-readable command-line arg errors, should be otherwise invisible.
+
+* the SolrJsonWriter now supports HTTP basic auth credentials embedded in `solr.url` or `solr.update_url`, eg `http://user:pass@example.org/solr` https://github.com/traject/traject/pull/262
+
+
+## 3.4.0
+
+* XML-mode `extract_xpath` now supports extracting attribute values with xpath @attr syntax.
 
 ## 3.3.0
 

data/README.md

@@ -8,8 +8,8 @@ Traject can also be generalized to a set of tools for getting structured data fr
 
 **Traject is stable, mature software, that is already being used in production by its authors and several other institutions.**
 
-[![Gem Version](https://badge.fury.io/rb/traject.png)](http://badge.fury.io/rb/traject)
-[![Build Status](https://travis-ci.org/traject/traject.png)](https://travis-ci.org/traject/traject)
+[![Gem Version](https://badge.fury.io/rb/traject.svg)](http://badge.fury.io/rb/traject)
+[![CI Status](https://github.com/traject/traject/workflows/CI/badge.svg?branch=master)](https://github.com/traject/traject/actions?query=workflow%3ACI+branch%3Amaster)
 
 
 ## Background/Goals
@@ -177,6 +177,11 @@ TranslationMap use above is just one example of a transformation macro, that tra
 * `split(" ")`: take values and split them, possibly result in multiple values.
 * `transform(proc)`: transform each existing macro using a proc, kind of like `map`.
    eg `to_field "something", extract_xml("//author"), transform( ->(author) { "#{author.last}, #{author.first}" })
+* `delete_if(["a", "b"])`: remove a value from accumulated values if it is included in the passed in argumet.
+    * Can also take a string, proc or regex as an argument. See [tests](test/indexer/macros/transformation_test.rb) for full functionality.
+* `select(proc)`: selects (keeps) values from accumulated values if proc evaluates to true for specifc value.
+    * Can also take a arrays, sets and regex as an argument. See [tests](test/indexer/macros/transformation_test.rb) for full functionality.
+
 
 You can add on as many transformation macros as you want, they will be applied to output in order.
 
@@ -468,6 +473,22 @@ Also see `-I load_path` option and suggestions for Bundler use under Extending W
 See also [Hints for batch and cronjob use](./doc/batch_execution.md) of traject.
 
 
+## A small but complete example
+
+To process a MARC XML file with the data shown in [./examples/marc/tiny.xml](./examples/marc/tiny.xml) you can use save the following configuration as `config.rb`:
+
+```
+to_field 'title', extract_marc('245a', first: true)
+```
+
+and run Traject as follows:
+
+```
+traject -t xml -c config.rb -w Traject::DebugWriter tiny.xml
+```
+
+`-t xml` indicates that the file is a MARC XML file. `-w Traject::DebugWriter` outputs the results to the console (e.g. without saving to Solr).
+
 ## Extending With Your Own Code
 
 Traject config files are full live ruby files, where you can do anything,

data/doc/settings.md

@@ -83,7 +83,8 @@ settings are applied first of all. It's recommended you use `provide`.
 ### Writing to solr
 
 * `json_writer.pretty_print`: used by the JsonWriter, if set to true, will output pretty printed json (with added whitespace) for easier human readability. Default false.
-* `solr.url`: URL to connect to a solr instance for indexing, eg http://example.org:8983/solr . Command-line short-cut `-u`.
+
+* `solr.url`: URL to connect to a solr instance for indexing, eg http://example.org:8983/solr . Command-line short-cut `-u`. (Can include embedded HTTP basic auth as eg `http://user:pass@example.org/solr`)
 
 * `solr.version`: Set to eg "1.4.0", "4.3.0"; currently un-used, but in the future will control some default settings, and/or sanity check and warn you if you're doing something that might not work with that version of solr. Set now for help in the future.
 
@@ -93,7 +94,8 @@ settings are applied first of all. It's recommended you use `provide`.
 
 * `solr_writer.thread_pool`: defaults to 1 (single bg thread). A thread pool is used for submitting docs to solr. Set to 0 or nil to disable threading. Set to 1, there will still be a single bg thread doing the adds. May make sense to set higher than number of cores on your indexing machine, as these threads will mostly be waiting on Solr. Speed/capacity of your solr might be more relevant. Note that processing_thread_pool threads can end up submitting to solr too, if solr_json_writer.thread_pool is full.
 
-* `solr_writer.basic_auth_user`, `solr_writer.basic_auth_password`: Not set by default but when both are set the default writer is configured with basic auth.
+* `solr_writer.basic_auth_user`, `solr_writer.basic_auth_password`: Not set by default but when both are set the default writer is configured with basic auth. You can also just embed basic
+auth credentials in `solr.url` using standard URI syntax.
 
 
 ### Dealing with MARC data

data/doc/xml.md

@@ -4,6 +4,8 @@ The [NokogiriIndexer](../lib/traject/nokogiri_indexer.md) is a Traject::Indexer
 
 It by default uses the NokogiriReader to read XML and read Nokogiri::XML::Documents, and includes the NokogiriMacros mix-in, with some macros for operating on Nokogiri::XML::Documents.
 
+Plese notice that the recommened mechanism to parse MARC XML files with Traject is via the `-t` parameter (or the via the `provide "marc_source.type", "xml"` setting). The documentation in this page is for those parsing other (non MARC) XML files.
+
 ## On the command-line
 
 You can tell the traject command-line to use the NokogiriIndexer with the `-i xml` flag:
@@ -72,6 +74,16 @@ You can use all the standard transforation macros in Traject::Macros::Transforma
 to_field "something", extract_xpath("//value"), first_only, translation_map("some_map"), default("no value")
 ```
 
+### selecting attribute values
+
+Just works, using xpath syntax for selecting an attribute:
+
+
+```ruby
+# gets status value in:  <oai:header status="something">
+to_field "status", extract_xpath("//oai:record/oai:header/@status")
+```
+
 
 ### selecting non-text nodes
 

data/examples/marc/tiny.xml

@@ -0,0 +1,35 @@
+<?xml version="1.0" encoding="UTF-8"?>
+<collection xmlns="http://www.loc.gov/MARC21/slim" xmlns:marc="http://www.loc.gov/MARC21/slim">
+ <record>
+  <leader>01352cam a2200349 a 4500</leader>
+  <datafield tag="245" ind1="0" ind2="0">
+   <subfield code="6">880-01</subfield>
+   <subfield code="a">Kazoku kankei no shakai shinrigaku /</subfield>
+   <subfield code="c">Osada Masayoshi hen.</subfield>
+  </datafield>
+ </record>
+ <record>
+  <leader>01121ccm a2200289z  4500</leader>
+  <datafield tag="245" ind1="1" ind2="0">
+   <subfield code="a">Powhatan&#39;s daughter :</subfield>
+   <subfield code="b">march</subfield>
+  </datafield>
+  <datafield tag="100" ind1="1" ind2=" ">
+   <subfield code="a">Sousa, John Philip,</subfield>
+   <subfield code="d">1854-1932,</subfield>
+   <subfield code="e">composer.</subfield>
+  </datafield>
+ </record>
+ <record>
+  <leader>01137cam a2200301 a 4500</leader>
+  <datafield tag="245" ind1="1" ind2="0">
+   <subfield code="a">Two pieces /</subfield>
+   <subfield code="c">by Frank O&#39;Hara.</subfield>
+  </datafield>
+  <datafield tag="100" ind1="1" ind2=" ">
+   <subfield code="a">O&#39;Hara, Frank,</subfield>
+   <subfield code="d">1926-1966.</subfield>
+   <subfield code="0">http://id.loc.gov/authorities/names/n79042130</subfield>
+  </datafield>
+ </record>
+</collection>

data/lib/traject/command_line.rb

@@ -29,10 +29,10 @@ module Traject
       self.console = $stderr
 
       self.orig_argv      = argv.dup
-      self.remaining_argv = argv
 
-      self.slop    = create_slop!
-      self.options = parse_options(self.remaining_argv)
+      self.slop    = create_slop!(argv)
+      self.options = self.slop
+      self.remaining_argv = self.slop.arguments
     end
 
     # Returns true on success or false on failure; may also raise exceptions;
@@ -40,11 +40,11 @@ module Traject
     def execute
       if options[:version]
         self.console.puts "traject version #{Traject::VERSION}"
-        return
+        return true
       end
       if options[:help]
-        self.console.puts slop.help
-        return
+        self.console.puts slop.to_s
+        return true
       end
 
 
@@ -179,11 +179,11 @@ module Traject
     end
 
     def arg_check!
-      if options[:command] == "process" && (options[:conf].nil? || options[:conf].length == 0)
+      if options[:command] == "process" && (!options[:conf] || options[:conf].length == 0)
         self.console.puts "Error: Missing required configuration file"
         self.console.puts "Exiting..."
         self.console.puts
-        self.console.puts self.slop.help
+        self.console.puts self.slop.to_s
         exit 2
       end
     end
@@ -234,28 +234,36 @@ module Traject
     end
 
 
-    def create_slop!
-      return Slop.new(:strict => true) do
-        banner "traject [options] -c configuration.rb [-c config2.rb] file.mrc"
+    def create_slop!(argv)
+      options = Slop::Options.new do |o|
+        o.banner = "traject [options] -c configuration.rb [-c config2.rb] file.mrc"
 
-        on 'v', 'version', "print version information to stderr"
-        on 'd', 'debug', "Include debug log, -s log.level=debug"
-        on 'h', 'help', "print usage information to stderr"
-        on 'c', 'conf', 'configuration file path (repeatable)', :argument => true, :as => Array
-        on :i, 'indexer', "Traject indexer class name or shortcut", :argument => true, default: "marc"
-        on :s, :setting, "settings: `-s key=value` (repeatable)", :argument => true, :as => Array
-        on :r, :reader, "Set reader class, shortcut for -s reader_class_name=", :argument => true
-        on :o, "output_file", "output file for Writer classes that write to files", :argument => true
-        on :w, :writer, "Set writer class, shortcut for -s writer_class_name=", :argument => true
-        on :u, :solr, "Set solr url, shortcut for -s solr.url=", :argument => true
-        on :t, :marc_type, "xml, json or binary. shortcut for -s marc_source.type=", :argument => true
-        on :I, "load_path", "append paths to ruby $LOAD_PATH", :argument => true, :as => Array, :delimiter => ":"
+        o.on '-v', '--version', "print version information to stderr"
+        o.on '-d', '--debug', "Include debug log, -s log.level=debug"
+        o.on '-h', '--help', "print usage information to stderr"
+        o.array '-c', '--conf', 'configuration file path (repeatable)', :delimiter => nil
+        o.string "-i", '--indexer', "Traject indexer class name or shortcut", :default => "marc"
+        o.array "-s", "--setting", "settings: `-s key=value` (repeatable)", :delimiter => nil
+        o.string "-r", "--reader", "Set reader class, shortcut for -s reader_class_name="
+        o.string "-o", "--output_file", "output file for Writer classes that write to files"
+        o.string "-w", "--writer", "Set writer class, shortcut for -s writer_class_name="
+        o.string "-u", "--solr", "Set solr url, shortcut for -s solr.url="
+        o.string "-t", "--marc_type", "xml, json or binary. shortcut for -s marc_source.type="
+        o.array "-I", "--load_path", "append paths to ruby $LOAD_PATH", :delimiter => ":"
 
-        on :x, "command", "alternate traject command: process (default); marcout; commit", :argument => true, :default => "process"
+        o.string "-x", "--command", "alternate traject command: process (default); marcout; commit", :default => "process"
 
-        on "stdin", "read input from stdin"
-        on "debug-mode", "debug logging, single threaded, output human readable hashes"
+        o.on "--stdin", "read input from stdin"
+        o.on "--debug-mode", "debug logging, single threaded, output human readable hashes"
       end
+
+      options.parse(argv)
+    rescue Slop::Error => e
+      self.console.puts "Error: #{e.message}"
+      self.console.puts "Exiting..."
+      self.console.puts
+      self.console.puts options.to_s
+      exit 1
     end
 
     def initialize_indexer!
@@ -267,22 +275,5 @@ module Traject
 
       return indexer
     end
-
-    def parse_options(argv)
-
-      begin
-        self.slop.parse!(argv)
-      rescue Slop::Error => e
-        self.console.puts "Error: #{e.message}"
-        self.console.puts "Exiting..."
-        self.console.puts
-        self.console.puts slop.help
-        exit 1
-      end
-
-      return self.slop.to_hash
-    end
-
-
   end
 end

data/lib/traject/debug_writer.rb

@@ -62,7 +62,7 @@ All records are assumed to have a unique id. You can set which field to look in
   def serialize(context)
     h       = context.output_hash
     rec_key = record_number(context)
-    lines   = h.keys.sort.map { |k| @format % [rec_key, k, h[k].join(' | ')] }
+    lines   = h.keys.sort.map { |k| @format % [rec_key, k, (h[k] || []).join(' | ')] }
     lines.push "\n"
     lines.join("\n")
   end

data/lib/traject/macros/marc21.rb

@@ -15,7 +15,7 @@ module Traject::Macros
     # field/substring specification.
     #
     # First argument is a string spec suitable for the MarcExtractor, see
-    # MarcExtractor::parse_string_spec.
+    # Traject::MarcExtractor::Spec.
     #
     # Second arg is optional options, including options valid on MarcExtractor.new,
     # and others. By default, will de-duplicate results, but see :allow_duplicates
@@ -42,11 +42,11 @@ module Traject::Macros
     #
     # * :translation_map => String: translate with named translation map looked up in load
     #       path, uses Tranject::TranslationMap.new(translation_map_arg).
-    #       **Instead**, use `extract_marc(whatever), translation_map(translation_map_arg)
+    #       **Instead**, use `extract_marc(whatever), translation_map(translation_map_arg)`
     #
     # * :trim_punctuation => true; trims leading/trailing punctuation using standard algorithms that
     #     have shown themselves useful with Marc, using Marc21.trim_punctuation. **Instead**, use
-    #    `extract_marc(whatever), trim_punctuation
+    #    `extract_marc(whatever), trim_punctuation`
     #
     # * :default => String: if otherwise empty, add default value. **Instead**, use `extract_marc(whatever), default("default value")`
     #

data/lib/traject/macros/marc21_semantics.rb

@@ -327,10 +327,14 @@ module Traject::Macros
       if field008 && field008.length >= 11
         date_type = field008.slice(6)
         date1_str = field008.slice(7,4)
-        date2_str = field008.slice(11, 4) if field008.length > 15
+        if field008.length > 15
+          date2_str = field008.slice(11, 4)
+        else
+          date2_str = date1_str
+        end
 
-        # for date_type q=questionable, we have a range.
-        if (date_type == 'q')
+        # for date_type q=questionable, we expect to have a range.
+        if date_type == 'q' and date1_str != date2_str
           # make unknown digits at the beginning or end of range,
           date1 = date1_str.sub("u", "0").to_i
           date2 = date2_str.sub("u", "9").to_i

data/lib/traject/macros/nokogiri_macros.rb

@@ -26,9 +26,15 @@ module Traject
             # Make sure to avoid text content that was all blank, which is "between the children"
             # whitespace.
             result = result.collect do |n|
-              n.xpath('.//text()').collect(&:text).tap do |arr|
-                arr.reject! { |s| s =~ (/\A\s+\z/) }
-              end.join(" ")
+              if n.kind_of?(Nokogiri::XML::Attr)
+                # attribute value
+                n.value
+              else
+                # text from node
+                n.xpath('.//text()').collect(&:text).tap do |arr|
+                  arr.reject! { |s| s =~ (/\A\s+\z/) }
+                end.join(" ")
+              end
             end
           else
             # just put all matches in accumulator as Nokogiri::XML::Node's

data/lib/traject/macros/transformation.rb

@@ -157,6 +157,36 @@ module Traject
           acc.collect! { |v| v.gsub(pattern, replace) }
         end
       end
+
+      # Run ruby `delete_if` on the accumulator for values that include or are equal to arg.
+      # It will also accept an array, set, regex pattern, proc or lambda as an arugment.
+      #
+      # @example
+      #   to_field "creator_facet", extract_marc("100abcdq"), delete_if(/foo/)
+      def delete_if(arg)
+        p = if arg.respond_to? :include?
+              proc { |v| arg.include?(v) }
+            else
+              proc { |v| arg === v }
+            end
+
+        ->(_, acc) { acc.delete_if(&p) }
+      end
+
+      # Run ruby `select!` on the accumulator for values that include or are equal to arg.
+      # It accepts an array, set, regex pattern, proc or lambda as an arugument.
+      #
+      # @example
+      #   to_field "creator_facet", extract_marc("100abcdq"), select(->(v) { v != "foo" })
+      def select(arg)
+        p = if arg.respond_to? :include?
+              proc { |v| arg.include?(v) }
+            else
+              proc { |v| arg === v }
+            end
+
+        ->(_, acc) { acc.select!(&p) }
+      end
     end
   end
 end

data/lib/traject/marc_extractor.rb

@@ -2,9 +2,9 @@ require 'traject/marc_extractor_spec'
 
 module Traject
   # MarcExtractor is a class for extracting lists of strings from a MARC::Record,
-  # according to specifications. See #parse_string_spec for description of string
-  # string arguments used to specify extraction. See #initialize for options
-  # that can be set controlling extraction.
+  # according to specifications. See Traject::MarcExtractor::Spec for description
+  # of string string arguments used to specify extraction. See #initialize for
+  # options that can be set controlling extraction.
   #
   # Examples:
   #

data/lib/traject/nokogiri_reader.rb

@@ -1,3 +1,5 @@
+require 'nokogiri'
+
 module Traject
   # A Trajet reader which reads XML, and yields zero to many Nokogiri::XML::Document
   # objects as source records in the traject pipeline.

data/lib/traject/solr_json_writer.rb

@@ -41,10 +41,12 @@ require 'concurrent' # for atomic_fixnum
 #
 # ## Relevant settings
 #
-# * solr.url (optional if solr.update_url is set) The URL to the solr core to index into
+# * solr.url (optional if solr.update_url is set) The URL to the solr core to index into.
+#   (Can include embedded HTTP basic auth as eg `http://user:pass@host/solr`)
 #
 # * solr.update_url: The actual update url. If unset, we'll first see if
-#   "#{solr.url}/update/json" exists, and if not use "#{solr.url}/update"
+#   "#{solr.url}/update/json" exists, and if not use "#{solr.url}/update". (Can include
+#   embedded HTTP basic auth as eg `http://user:pass@host/solr)
 #
 # * solr_writer.batch_size: How big a batch to send to solr. Default is 100.
 #   My tests indicate that this setting doesn't change overall index speed by a ton.
@@ -101,12 +103,17 @@ class Traject::SolrJsonWriter
   def initialize(argSettings)
     @settings = Traject::Indexer::Settings.new(argSettings)
 
+
     # Set max errors
     @max_skipped = (@settings['solr_writer.max_skipped'] || DEFAULT_MAX_SKIPPED).to_i
     if @max_skipped < 0
       @max_skipped = nil
     end
 
+
+    # Figure out where to send updates, and if with basic auth
+    @solr_update_url, basic_auth_user, basic_auth_password = self.determine_solr_update_url
+
     @http_client = if @settings["solr_json_writer.http_client"]
       @settings["solr_json_writer.http_client"]
     else
@@ -115,9 +122,8 @@ class Traject::SolrJsonWriter
         client.connect_timeout = client.receive_timeout = client.send_timeout = @settings["solr_writer.http_timeout"]
       end
 
-      if @settings["solr_writer.basic_auth_user"] &&
-          @settings["solr_writer.basic_auth_password"]
-        client.set_auth(@settings["solr.url"], @settings["solr_writer.basic_auth_user"], @settings["solr_writer.basic_auth_password"])
+      if basic_auth_user || basic_auth_password
+        client.set_auth(@solr_update_url, basic_auth_user, basic_auth_password)
       end
 
       client
@@ -143,13 +149,11 @@ class Traject::SolrJsonWriter
     # this the new default writer.
     @commit_on_close = (settings["solr_writer.commit_on_close"] || settings["solrj_writer.commit_on_close"]).to_s == "true"
 
-    # Figure out where to send updates
-    @solr_update_url = self.determine_solr_update_url
 
     @solr_update_args = settings["solr_writer.solr_update_args"]
     @commit_solr_update_args = settings["solr_writer.commit_solr_update_args"]
 
-    logger.info("   #{self.class.name} writing to '#{@solr_update_url}' in batches of #{@batch_size} with #{@thread_pool_size} bg threads")
+    logger.info("   #{self.class.name} writing to '#{@solr_update_url}' #{"(with HTTP basic auth)" if basic_auth_user || basic_auth_password}in batches of #{@batch_size} with #{@thread_pool_size} bg threads")
   end
 
 
@@ -368,13 +372,27 @@ class Traject::SolrJsonWriter
   end
 
 
-  # Relatively complex logic to determine if we have a valid URL and what it is
+  # Relatively complex logic to determine if we have a valid URL and what it is,
+  # and if we have basic_auth info
+  #
+  # Empties out user and password embedded in URI returned, to help avoid logging it.
+  #
+  # @returns [update_url, basic_auth_user, basic_auth_password]
   def determine_solr_update_url
-    if settings['solr.update_url']
+    url = if settings['solr.update_url']
       check_solr_update_url(settings['solr.update_url'])
     else
       derive_solr_update_url_from_solr_url(settings['solr.url'])
     end
+
+    parsed_uri                            = URI.parse(url)
+    user_from_uri, password_from_uri      = parsed_uri.user, parsed_uri.password
+    parsed_uri.user, parsed_uri.password  = nil, nil
+
+    basic_auth_user     = @settings["solr_writer.basic_auth_user"] || user_from_uri
+    basic_auth_password = @settings["solr_writer.basic_auth_password"] || password_from_uri
+
+    return [parsed_uri.to_s, basic_auth_user, basic_auth_password]
   end
 
 

data/lib/traject/version.rb

@@ -1,3 +1,3 @@
 module Traject
-  VERSION = "3.3.0"
+  VERSION = "3.7.0"
 end